Forschungsbericht 2025

Massively Parallel Systems E-EXK5

Leitung: Lal, Sohan
Gründungsdatum: 1.9.2021

Institut auf TORE
Institutswebsite

The institute of Massively Parallel Systems (MPS) investigates and teaches in the field of computer architecture, focussing on massively parallel systems.
These days massively parallel systems are present everywhere – in our smartphones, cars, supercomputers. They help us to do many things which were not possible before. For example, the recent stupendous success of machine learning, especially deep learning, is mainly due to the exponential increase in computational power. As such, machine learning is not new. Machine learning methods are around since the 1950s. What has predominately changed now is the computing power, with many-core processors such as GPUs as the main drivers. If these massively parallel processors are not utilized properly, they are very expensive in terms of power and energy consumption, which is not good as we aspire to reduce our carbon footprint. At MPS, we are working to make computing devices more performance and energy-efficient from the architecture perspective, and improve their programmability from a programmer’s perspective.

Publikationen

• A portable compiler-runtime approach for scalability prediction - Journal Article
  Stawinoga, Nicolai; Lal, Sohan; Cosenza, Biagio; Salzmann, Philip; Thoman, Peter; Fahringer, Thomas
  Future Generation Computer Systems 179: 108337 (2026)
  Open Access | Publisher DOI
  
  
• Robust LFSR-based scrambling to mitigate stencil attack on main memory - Journal Article
  Kumar, Gaurav; Nanote, Kushal Pravin; Lal, Sohan; Prasad, Yamuna; Ahlawat, Satyadev
  ACM Transactions on Embedded Computing Systems 24 (5s): 102 (2025)
  Open Access | Publisher DOI
  
  
• On enhancing the security against memory disclosure attacks - Conference Paper
  Ghosh, Prokash; Kumar, Gaurav; Lal, Sohan; Ahlawat, Satyadev; Virendra Singh
  IEEE 38th International System-on-Chip Conference, SOCC 2025
  Publisher DOI
  
  
• Enhancing Practicality of Memory Compression for GPUs with High-Throughput Simplifications - Conference Paper
  Renz, Manuel; Lal, Sohan
  22nd ACM International Conference on Computing Frontiers, CF 2025
  Open Access | Publisher DOI
  
  
• AI-driven anomaly detection in oscilloscope images for post-silicon validation - Conference Paper
  Akash, Kowshic A.; Wulf, Tobias; Valentin, Torsten; Geist, Alexander; Kulau, Ulf; Lal, Sohan
  38th International Conference on VLSI Design and 24th International Conference on Embedded Systems, VLSID 2025
  Open Access | Publisher DOI
  
  
• Case Study: AI-Driven Log Extraction and Trace Outlier Detection for Efficient Post-Silicon Validation - Conference Paper
  Akash, Kowshic A.; Wulf, Tobias; Valentin, Torsten; Geist, Alexander; Kulau, Ulf; Jose, John; Lal, Sohan
  26th IEEE Latin-American Test Symposium, LATS 2025
  Open Access | Publisher DOI
  
  
• ClusterSim: modeling thread block clusters in hopper GPUs - Conference Paper
  Lühnen, Tim Julius; Behera, Jyotirman; Tripathy, Devashree; Lal, Sohan
  IEEE International Symposium on Workload Characterization, IISWC 2025
  Open Access | Publisher DOI